Deerwalk's latest release makes new data fields available along with a model that predicts the likelihood a member will have an inpatient admission event 

Below are the key highlights from this month’s release of Deerwalk Plan Analytics:

1. NEW DATA ENRICHMENT 
2. NEW MACHINE LEARNING MODEL: INPATIENT ADMISSION PREDICTION 

1. NEW DATA ENRICHMENT

Deerwalk takes in data from a multitude of different sources and runs it through a series of scrub and enrichment processes to generate insights into the health and risk of a population. After these processes are complete, the enriched data is made available within Deerwalk Plan Analytics, represented by fields that can be easily searched or reported on from various modules within the application. With this release, we've added multiple data fields:

• The “Chronic Conditions” field displays the chronic conditions a member had at the date a specific claim was serviced.
• The “Member Paid” field displays the sum of the coinsurance, co-payment, and deductible fields for a specific claim. 
• The “Event Type” field indicates whether or not a record was paid and reversed (i.e., reversal), unpaid, or neither.
• The “Event Count” field corresponds with the “Event Type” field and assigns a number based on the payment status of the event.  

2. NEW MACHINE LEARNING MODEL: INPATIENT ADMISSION PREDICTION

We’ve released a sixth machine learning model, the Inpatient Admission Prediction Model, which helps predict the likelihood a member will have an inpatient admission event within the next 24 months. The model can be used to identify members at a high risk of future inpatient utilization and stratify populations based on their likelihood of admissions. The “Admission Probability (AI)” field can be accessed from the Member Search Module and the Create Module within Deerwalk Plan Analytics.

• The field value is generated for each member based on their medical, eligibility, and pharmacy claims history for the past one year (12 months).
• A probability score greater than 0.5 indicates a member is likely to have an admission within the next 24 months while a score lower than 0.5 indicates a member is not likely to have an admission.
• The existing “Inpatient Admission Probability” field derived from the MARA model will continue to be available within the application.

Schedule a demo to learn more about how to use Deerwalk Plan Analytics and the latest features.

Subscribe to our blog or follow us on Facebook, Twitter or LinkedIn to join the conversation.